© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4486
    Prev
    Next
    INDEX
    Explanations

    code or math expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    הערות
    -0.46
    .
    -0.38
     produisons
    -0.36
     month
    -0.36
    go
    -0.36
    and
    -0.35
     IActionResult
    -0.35
     lunak
    -0.35
     just
    -0.34
    .)
    -0.34
    POSITIVE LOGITS
     disambiguazione
    0.90
     насељу
    0.85
    SBATCH
    0.82
    osoba
    0.76
    MessageOf
    0.75
    transQ
    0.75
    expandindo
    0.75
    yntaxException
    0.72
     initComponents
    0.71
    PreferredItem
    0.71
    Activations Density 0.022%

    No Known Activations